LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Cosmic 2 by Tilo15

 »  All LLMs  »  Tilo15  »  Cosmic 2   URL Share it on

  10   

Cosmic 2 is an open-source language model by Tilo15. Features: 7.2b LLM, VRAM: 14.4GB, License: other, Quantized, LLM Explorer Score: 0.14.

  Autotrain Base model:quantized:tilo15/bi...   Base model:tilo15/big-text-3   Conversational   Endpoints compatible   Ggml   Gguf   Imatrix   Lora   Mistral   Peft   Quantized   Region:us   Safetensors   Sharded   Tensorboard   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Tilo15/cosmic-2 

Cosmic 2 Benchmarks

LLME Score: 0.14126
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Cosmic 2 (Tilo15/cosmic-2)
🌟 Advertise your project 🚀

Cosmic 2 Parameters and Internals

Model Type 
text-generation
Additional Notes 
Model Trained Using AutoTrain. For more information, please visit AutoTrain: https://hf.co/docs/autotrain
Training Details 
Methodology:
Model trained using AutoTrain.
LLM NameCosmic 2
Repository 🤗https://huggingface.co/Tilo15/cosmic-2 
Base Model(s)  Tilo15/big-text-3   Tilo15/big-text-3
Model Size7.2b
Required VRAM14.4 GB
Updated2026-04-10
MaintainerTilo15
Model Files  0.2 GB   0.5 GB: 1-of-9   0.5 GB: 2-of-9   0.5 GB: 3-of-9   0.5 GB: 4-of-9   0.5 GB: 5-of-9   0.5 GB: 6-of-9   0.5 GB: 7-of-9   0.5 GB: 8-of-9   0.2 GB: 9-of-9   1.8 GB   4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3   0.0 GB
GGML QuantizationYes
GGUF QuantizationYes
Quantization Typeggml|gguf
Model ArchitectureAutoModelForCausalLM
Licenseother
Is Biasednone
Tokenizer ClassLlamaTokenizer
Padding Token</s>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesgate_proj|down_proj|v_proj|up_proj|o_proj|k_proj|q_proj
LoRA Alpha32
LoRA Dropout0.05
R Param16

Best Alternatives to Cosmic 2

Best Alternatives
Context / RAM
Downloads
Likes
Mistralmeme0K / 14.4 GB660
Mistral7b V0.3 Alpaca Cleaned0K / 14.5 GB100
My Mistral Seekh Qna0K / 28.9 GB310
Zephyr Tuning V10K / 14.4 GB17470
Spydaz Web AI 0250K / 14.4 GB440
Small Fut Final0K / 14.4 GB111
Last Model Too Long Time0K / 14.4 GB81
Big Fut Final0K / 14.4 GB21
DummySFT0K / 28.9 GB60
Ethicalsft0K / 28.9 GB60
Note: green Score (e.g. "73.2") means that the model is better than Tilo15/cosmic-2.

Rank the Cosmic 2 Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 52721 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer